train.log
Browse files
train.log
CHANGED
|
@@ -34,3 +34,20 @@
|
|
| 34 |
[12:28:18] val/lichess_opening hard_ce=1.5239 soft_ce=1.5239 soft_temp_ce=1.5239 teacher_entropy=0.0000 teacher_kl=1.5239 wdl_ce=1.0404 value_rows=8192.0000
|
| 35 |
[12:28:40] step 225/8000 | loss=1.8335 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=118800/0/0 q=0 p=0 | 488 pos/s | vram=35.72GB
|
| 36 |
[12:28:44] soft inbox +640,000 train_n=6,144,283 shards=shard_000069,shard_000070,shard_000071,shard_000072,shard_000073,shard_000074,shard_000075,shard_000076
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
[12:28:18] val/lichess_opening hard_ce=1.5239 soft_ce=1.5239 soft_temp_ce=1.5239 teacher_entropy=0.0000 teacher_kl=1.5239 wdl_ce=1.0404 value_rows=8192.0000
|
| 35 |
[12:28:40] step 225/8000 | loss=1.8335 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=118800/0/0 q=0 p=0 | 488 pos/s | vram=35.72GB
|
| 36 |
[12:28:44] soft inbox +640,000 train_n=6,144,283 shards=shard_000069,shard_000070,shard_000071,shard_000072,shard_000073,shard_000074,shard_000075,shard_000076
|
| 37 |
+
[12:29:06] step 250/8000 | loss=1.8117 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=132000/0/0 q=0 p=0 | 490 pos/s | vram=35.72GB
|
| 38 |
+
[12:29:10] soft inbox +400,000 train_n=6,544,283 shards=shard_000077,shard_000078,shard_000079,shard_000080,shard_000081
|
| 39 |
+
[12:29:33] step 275/8000 | loss=1.8019 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=145200/0/0 q=0 p=0 | 490 pos/s | vram=35.72GB
|
| 40 |
+
[12:29:36] soft inbox +420,822 train_n=6,965,105 shards=shard_000082,shard_000083,shard_000084,shard_000085,shard_000086,shard_000087
|
| 41 |
+
[12:29:59] step 300/8000 | loss=1.8165 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=158400/0/0 q=0 p=0 | 492 pos/s | vram=35.72GB
|
| 42 |
+
[12:30:02] soft inbox +480,000 train_n=7,445,105 shards=shard_000088,shard_000089,shard_000090,shard_000091,shard_000092,shard_000093
|
| 43 |
+
[12:30:03] ckpt step_000300.pt + latest.pt (live) steps=300 status=mid kind=full
|
| 44 |
+
[12:30:12] val/lichess_opening hard_ce=1.5221 soft_ce=1.5221 soft_temp_ce=1.5221 teacher_entropy=0.0000 teacher_kl=1.5221 wdl_ce=1.0390 value_rows=8192.0000
|
| 45 |
+
[12:30:34] step 325/8000 | loss=1.8078 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=171600/0/0 q=0 p=0 | 481 pos/s | vram=35.72GB
|
| 46 |
+
[12:30:37] soft inbox +560,000 train_n=8,005,105 shards=shard_000094,shard_000095,shard_000096,shard_000097,shard_000098,shard_000099,shard_000100
|
| 47 |
+
[12:31:00] step 350/8000 | loss=1.8217 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=184800/0/0 q=0 p=0 | 483 pos/s | vram=35.72GB
|
| 48 |
+
[12:31:04] soft inbox +480,000 train_n=8,485,105 shards=shard_000101,shard_000102,shard_000103,shard_000104,shard_000105,shard_000106
|
| 49 |
+
[12:31:26] step 375/8000 | loss=1.8192 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=198000/0/0 q=0 p=0 | 484 pos/s | vram=35.72GB
|
| 50 |
+
[12:31:31] soft inbox +480,000 train_n=8,965,105 shards=shard_000107,shard_000108,shard_000109,shard_000110,shard_000111,shard_000112
|
| 51 |
+
[12:31:53] step 400/8000 | loss=1.8309 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=211200/0/0 q=0 p=0 | 484 pos/s | vram=35.72GB
|
| 52 |
+
[12:31:59] soft inbox +480,000 train_n=9,445,105 shards=shard_000113,shard_000114,shard_000115,shard_000116,shard_000117,shard_000118
|
| 53 |
+
[12:32:08] val/lichess_opening hard_ce=1.5139 soft_ce=1.5139 soft_temp_ce=1.5139 teacher_entropy=0.0000 teacher_kl=1.5139 wdl_ce=1.0394 value_rows=8192.0000
|